This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Measuring the Objectness of Image Windows
Nov. 2012 (vol. 34 no. 11)
pp. 2189-2202
B. Alexe, Comput. Vision Lab., ETH Zurich, Zurich, Switzerland
T. Deselaers, Google Switzerland, Zurich, Switzerland
V. Ferrari, IPAB Inst., Univ. of Edinburgh, Edinburgh, UK
We present a generic objectness measure, quantifying how likely it is for an image window to contain an object of any class. We explicitly train it to distinguish objects with a well-defined boundary in space, such as cows and telephones, from amorphous background elements, such as grass and road. The measure combines in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary. These include an innovative cue to measure the closed boundary characteristic. In experiments on the challenging PASCAL VOC 07 dataset, we show this new cue to outperform a state-of-the-art saliency measure, and the combined objectness measure to perform better than any cue alone. We also compare to interest point operators, a HOG detector, and three recent works aiming at automatic object segmentation. Finally, we present two applications of objectness. In the first, we sample a small numberof windows according to their objectness probability and give an algorithm to employ them as location priors for modern class-specific object detectors. As we show experimentally, this greatly reduces the number of windows evaluated by the expensive class-specific model. In the second application, we use objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives. As shown in several recent papers, objectness can act as a valuable focus of attention mechanism in many other applications operating on image windows, including weakly supervised learning of object categories, unsupervised pixelwise segmentation, and object tracking in video. Computing objectness is very efficient and takes only about 4 sec. per image.
Index Terms:
Detectors,Image edge detection,Image segmentation,Kernel,Image color analysis,Training,Area measurement,object recognition,Objectness measure,object detection
Citation:
B. Alexe, T. Deselaers, V. Ferrari, "Measuring the Objectness of Image Windows," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2189-2202, Nov. 2012, doi:10.1109/TPAMI.2012.28
Usage of this product signifies your acceptance of the Terms of Use.